AI Platform Engineer (AI+DevOps)

Here is the JD -

The AI Platform Engineer (AI with DevOps) will join the AI Enablement team, focusing on building, maintaining, and scaling enterprise AI infrastructure. This includes proprietary agent orchestration platforms (NOVA), AI gateway services, and Retrieval-Augmented Generation (RAG) pipelines across multi-cloud environments.

Key Responsibilities:

• Platform Development & Operations:
• Develop, deploy, and maintain the NOVA agentic AI platform
• Manage LiteLLM as the central AI gateway
• Optimize LLM routing, cost control, load balancing, and failover
• Implement monitoring and observability (Prometheus, Grafana, OpenTelemetry)
• RAG Pipeline Development:
• Design and optimize RAG pipelines
• Maintain document ingestion, chunking, embeddings, and vector stores
• Build RAG on GCP and Azure using managed AI services and vector databases
• Infrastructure & DevOps:
• Deploy AI services on Kubernetes (AKS, GKE)
• Implement CI/CD with Jenkins, Opsera, GitHub Actions
• Automate infrastructure (Terraform, Helm, GitOps)
• Ensure security and compliance
• Agentic AI & Automation:
• Develop automation tools and scripts
• Build MCP servers for tool integrations
• Enable multi-agent orchestration and autonomous workflows
• Create SDKs, APIs, and developer documentation

Required Qualifications:

• 5+ years platform engineering/DevOps experience
• 2+ years AI/ML or LLM platform experience
• Strong Kubernetes, CI/CD, and cloud experience (GCP or Azure)
• Proficiency in Python and/or TypeScript

Preferred Qualifications:

• Experience with LangChain, LlamaIndex, or agent frameworks
• Familiarity with LiteLLM, MCP, Backstage
• Cost optimization for LLM workloads
• Enterprise-scale AI platform experience

Technical Environment:

• AI Platforms: LiteLLM, LangChain, LangGraph
• Cloud: GCP, Azure
• Containers: Kubernetes, Docker, Helm
• CI/CD: Jenkins, GitHub Actions, Opsera
• Observability: Prometheus, Grafana, OpenTelemetry, Dynatrace
• Languages: Python, TypeScript, Bash